{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/census/gaussian","entry":"gaussian","source":"Syntology differential census (groundwork/55, run v2_2026-09-22), per sample; not an archive number","census_date":"2026-09-22","battery_sha256":["b986f7e04d794a0d88ad4c5f32cf63ec3590b5deff0192150737bc5f1c0b4677"],"runner_sha256":["5a452d0e7c0da5b80771d1be2afe3572e253568cf5c5d59a0d08ebd663d00808"],"bucket_key":"positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name","bucket_fields":["rank","kind","dtype"],"claim":"Implementations sharing this entry name were each run on one shared input fixed by the positional (rank, kind, dtype) of their array arguments (the bucket). A cluster is the set whose recorded output digest (sha256 of the output rounded to 6 decimals) is identical. Identical values to six decimals on the shared input are agreement on those inputs, not a statement about the whole domain and not a substitution claim.","n_implementations_compared":8,"n_papers":9,"n_buckets":4,"n_distinct_outputs":8,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":0,"by_error":{}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":3,"n_papers":8,"recorded_shared_digest_equals_own_fixture_digest":3},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/gaussian","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"74a713fcacae7558","size":1,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.2213115096092224,-0.2601047158241272,0.8380206227302551,-0.5774351358413696,-0.4418703317642212,-0.38714563846588135,-0.6019402146339417,0.6963692307472229,0.7688589692115784,0.4159351587295532,-1.0043878555297852,-0.2543710768222809,-1.38264799118042,0.17180179059505463,-0.7749705910682678,0.7246534824371338,6.008581638336182,-0.2458244264125824,0.9232397675514221,-0.9821672439575195,-17.656831741333008,-0.3378627896308899,-0.743091881275177,0.405563622713089,-0.5014278888702393,0.9207615256309509,0.4221712052822113,0.39207398891448975,-0.3254585564136505,0.313088059425354,-0.3017212450504303,-0.6714969277381897],"values_recorded":32,"members":[{"code_sha256_prefix":"294ba20b052bfbc7","path":"graphormer/models/IEFormer_ep_pp_deq.py","papers":["2510.27497","2303.02875","2606.18703"],"paper_pages":[{"arxiv_id":"2510.27497","page":"/paper/arxiv-2510-27497"},{"arxiv_id":"2303.02875","page":"/paper/dr-label-improving-gnn-models-for-catalysis"},{"arxiv_id":"2606.18703","page":"/paper/arxiv-2606-18703"}],"arg_sig_recorded":[["x",2,"float","float32"],["mean",2,"float","float32"],["std",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"0af269745b695fda","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.22131142020225525,-0.26010462641716003,0.838020384311676,-0.5774348974227905,-0.44187018275260925,-0.3871454894542694,-0.6019399762153625,0.6963690519332886,0.7688586711883545,0.41593506932258606,-1.0043874979019165,-0.2543710172176361,-1.3826473951339722,0.17180173099040985,-0.774970293045044,0.7246531844139099,6.008579730987549,-0.24582432210445404,0.9232394695281982,-0.9821668863296509,-17.65682601928711,-0.33786264061927795,-0.7430915832519531,0.40556344389915466,-0.5014277100563049,0.920761227607727,0.42217111587524414,0.3920738399028778,-0.32545843720436096,0.31308797001838684,-0.30172112584114075,-0.6714966893196106],"values_recorded":32,"members":[{"code_sha256_prefix":"e0552067b0269afd","path":"FCN_Image_Classification/BBB.py","papers":["1505.05424"],"paper_pages":[{"arxiv_id":"1505.05424","page":"/paper/weight-uncertainty-in-neural-networks"}],"arg_sig_recorded":[["x",2,"float","float32"],["mu",2,"float","float32"],["sigma",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"ea7df3f4d392d884","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.22131140530109406,-0.26010459661483765,0.8380202651023865,-0.5774348974227905,-0.44187021255493164,-0.3871454894542694,-0.6019399166107178,0.6963689923286438,0.7688586711883545,0.41593503952026367,-1.0043874979019165,-0.2543709874153137,-1.3826473951339722,0.17180171608924866,-0.7749702334403992,0.7246531248092651,6.008579730987549,-0.24582430720329285,0.9232394099235535,-0.9821667671203613,-17.656824111938477,-0.33786264061927795,-0.7430915236473083,0.40556344389915466,-0.5014276504516602,0.920761227607727,0.42217108607292175,0.3920738101005554,-0.3254584074020386,0.31308794021606445,-0.30172112584114075,-0.6714966297149658],"values_recorded":32,"members":[{"code_sha256_prefix":"8b551e1b6055d214","path":"spikegcl/model.py","papers":["2305.19306"],"paper_pages":[{"arxiv_id":"2305.19306","page":"/paper/a-graph-is-worth-1-bit-spikes-when-graph"}],"arg_sig_recorded":[["x",2,"float","float32"],["mu",2,"float","float32"],["sigma",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":2,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"08c8f5efe272100f","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.021896063995546163,0.4888606694904004,1.506296460454725,0.03670207114257604,0.22267663507922542,0.3896254513297066,0.000955711138186002,0.2219323734036242],"values_recorded":8,"members":[{"code_sha256_prefix":"dc85e687f1fe54a1","path":"constrainednmf/example_scripts/simulation_constraining_components.py","papers":["2104.00864"],"paper_pages":[{"arxiv_id":"2104.00864","page":"/paper/constrained-non-negative-matrix-factorization"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"mu":"1.5","sig":"0.8","a":"2.0"},"class_bearing":false}]},{"output_sha":"9b4cd0e5cda7e4ec","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.010948031997773082,0.2444303347452002,0.7531482302273625,0.01835103557128802,0.11133831753961271,0.1948127256648533,0.000477855569093001,0.1109661867018121],"values_recorded":8,"members":[{"code_sha256_prefix":"bfb5a3349111c442","path":"constrainednmf/example_scripts/simulation_constraining_weights.py","papers":["2104.00864"],"paper_pages":[{"arxiv_id":"2104.00864","page":"/paper/constrained-non-negative-matrix-factorization"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"mu":"1.5","sig":"0.8"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"473ebbe61ebcfaf2","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6767888069152832,-2.686136484146118,0.22547465562820435,-1.1247658729553223,-0.054139137268066406,-0.3384619951248169,-0.9787737131118774,-1.5423303842544556,0.8411508798599243,-0.3041890859603882,-0.04721638560295105,-1.2602143287658691,-0.16869357228279114,3.5597667694091797,0.601993203163147,0.3032509386539459,-1.286258339881897,-3.3188068866729736,0.9987618923187256,0.3873225450515747,0.5762452483177185,-2.735877513885498,-0.8782285451889038,2.8366804122924805,-0.04542338848114014,-0.15222272276878357,0.7715807557106018,1.2009961605072021,0.16358041763305664,2.8605523109436035,-0.3759235143661499,-1.4377858638763428],"values_recorded":32,"members":[{"code_sha256_prefix":"f905d3e3176ada9f","path":"model_cGAN.py","papers":["1411.1784"],"paper_pages":[{"arxiv_id":"1411.1784","page":"/paper/conditional-generative-adversarial-nets"}],"arg_sig_recorded":[["ins",2,"float","float32"]],"scalar_args":{"mean":"0.0","stddev":"1.0"},"class_bearing":false}]},{"output_sha":"57d42d1d3ad8c246","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0012008431367576122,0.007221225183457136,0.5071012377738953,0.3071432113647461,0.15628628432750702,0.0954136848449707,0.33144432306289673,0.4138732850551605,0.465680330991745,0.12672801315784454,0.5819758176803589,0.005827171728014946,0.6755039095878601,1.6532714653294533e-05,0.4696364104747772,0.43519774079322815,0.7908807396888733,0.004114484880119562,0.5492333769798279,0.573633074760437,0.797070324420929,0.04908088222146034,0.4483206868171692,0.11520741879940033,0.22496941685676575,0.5481289029121399,0.13375341892242432,0.10061255842447281,0.0395222045481205,0.03102213330566883,0.02417750470340252,0.3938746154308319],"values_recorded":32,"members":[{"code_sha256_prefix":"de8d7a878d027579","path":"s_mnist-gpu.py","papers":["2005.11633"],"paper_pages":[{"arxiv_id":"2005.11633","page":"/paper/effective-and-efficient-computation-with"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"mu":"0.0","sigma":"0.5"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"537a5b67f26bd2d2","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6065306597126334,0.6065306597126334,0.6065306597126334,0.6065306597126334,0.6065306597126334,0.6065306597126334,0.6065306597126334,0.6065306597126334],"values_recorded":8,"members":[{"code_sha256_prefix":"ed9db0e187d4afab","path":"model/model.py","papers":["1603.08511"],"paper_pages":[{"arxiv_id":"1603.08511","page":"/paper/colorful-image-colorization"}],"arg_sig_recorded":[["x",1,"float","float64"],["sig",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]}]}